高斯溅射重建中基于频率的视角选择
Frequency-based View Selection in Gaussian Splatting Reconstruction
AI总结：
针对3D高斯溅射重建中的主动视角选择问题，提出一种基于频域排序的方法，在无真实数据下有效估计新视角的信息增益，克服了现有模型架构限制并取得了最先进的结果。
摘要：
三维重建是机器人感知中的一个基本问题。我们研究了主动视角选择问题，旨在使用尽可能少的输入图像来完成3D Gaussian Splatting（3D高斯溅射）重建。尽管3D Gaussian Splatting在图像渲染和三维重建方面取得了显著进展，但重建质量在很大程度上受到二维图像的选择以及通过Structure-from-Motion (SfM) 算法估计相机位姿的影响。目前依赖于遮挡、深度模糊的不确定性或直接依赖神经网络预测的视角选择方法，不足以解决该问题，且难以泛化到新场景。通过在频域中对潜在视角进行排序，我们能够在没有真实数据的情况下，有效估计新视角的潜在信息增益。通过克服当前对模型架构和效能的限制，我们的方法在视角选择上取得了最先进的结果，展示了其在高效的基于图像的三维重建中的潜力。
英文摘要：
Three-dimensional reconstruction is a fundamental problem in robotics perception. We examine the problem of active view selection to perform 3D Gaussian Splatting reconstructions with as few input images as possible. Although 3D Gaussian Splatting has made significant progress in image rendering and 3D reconstruction, the quality of the reconstruction is strongly impacted by the selection of 2D images and the estimation of camera poses through Structure-from-Motion (SfM) algorithms. Current methods to select views that rely on uncertainties from occlusions, depth ambiguities, or neural network predictions directly are insufficient to handle the issue and struggle to generalize to new scenes. By ranking the potential views in the frequency domain, we are able to effectively estimate the potential information gain of new viewpoints without ground truth data. By overcoming current constraints on model architecture and efficacy, our method achieves state-of-the-art results in view selection, demonstrating its potential for efficient image-based 3D reconstruction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
